NONOGRAMS BENCHMARK · REASONING MEDIUM

GPT-6 Luna

Openai · released 2026-09-22 · route gpt-6-luna · Model profile · Chess results · Sudoku results · Mines results · FreeCell results · Starjar results · Nations Royale results · Wildhaven results · Hustle Sim results · Elemental Armory results · Micro Mouse results

Results

Score
1795%: 0 to 38 · 6 of 36 base puzzles so far
Puzzles solved
1 of 6
Cells that match the solution
1.6%
Rows and columns whose clue it satisfies
5.6%
Wrong cells / left cells unknown / no grid
0 / 5 / 0
Near misses (three cells or fewer wrong)
0
Average stated confidence
17%
Average confidence when it had not solved it
0%
Sure but wrong (90% or more, unsolved)
0
Calibration (Brier, lower is better)
0.000
API-equivalent cost per solved puzzle
$0.0092
Tokens per puzzle (in / out)
27,473 / 1,375
Reasoning tokens per puzzle
350
Retries for an unreadable reply
1
API-equivalent cost per puzzle
$0.0015
Seconds per puzzle
13.3
Replies cut off at the length limit
0.0%
Aborted on our side (not counted)
0

By tier

TierNeedsSolvedOutput tokensSeconds
5 by 5Line logic, a round or two1 of 13266.1
10 by 10Line logic, about 3 rounds0 of 11,34814.3
15 by 15Line logic, about 5 rounds0 of 11,38612.8
20 by 20Line logic, about 8 rounds0 of 12,48922.8
25 by 25Line logic, about 11 rounds0 of 11,0629.8
BeyondLine logic stalls; needs contradiction or search0 of 11,64114.0

Cells by the depth of logic they need

Each cell is tagged with the round of line logic that settles it. Beyond line logic means only contradiction or search does.

DepthCellsRight
First pass4033.7%
Rounds 2-36131.6%
Rounds 4-73320.0%
Round 8 on1590.0%
Beyond line logic930.0%

Every puzzle